Building agents

38,442 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

agentic-income

5569

frankxai/agentic-income-skills

Skill Claude CodeCodex

Build and operate principal-owned AI income systems that perform accepted paid work. Use when discovering an agent service opportunity, validating demand, creating an Outcome Pack, implementing a vertical AI system, defining agent authority, evaluating delivery, exposing a Skill/MCP/A2A service, or proving net…

not rated 2 8d ago A 96 tokens original MIT

agent-harness

5570

SUNRNEHUI/agent-harness

Skill Codex

A set of rules for coordinating coding work between multiple AI agents. It turns a request into an agreed plan, defines what counts as success, and supports work that can pause and continue later.

not rated 2 20d ago A 77 tokens original MIT

Project-Aura

5571

bryanchen3777/Project-Aura

Skill Claude CodeCodex

Project Aura is a lightweight AI emotional behavior plugin framework that adds an "Emotional Presentation Layer" to AI companions. It provides 7 distinct personality modules including admiration, vulnerability, coquettishness, comfort, flirting, transcendence, and ice-breaking.

not rated 2 5mo ago A 0 tokens

repo-knowledge

5574

Sixz-AI/repo-knowledge

Plugin Claude Code

Bundles 9 skills, 2 agents, 1 hook · 802 tokens together

Progressive codebase knowledge base — clone git repos, auto-generate documentation, and build a searchable knowledge cache that grows smarter with every query.

not rated 2 4mo ago A tokens not measured original MIT

aw-author

5575

zircote-plugins/github-agentic-workflows

Plugin Claude Code

Bundles 3 skills, 6 commands, 1 agent · 558 tokens together

Guided authoring, validation, and refinement of GitHub Agentic Workflow (gh-aw) markdown files. Includes fully autonomous daily intelligence pipeline (research, gap analysis, implementation, PR to develop), ecosystem monitoring, knowledge base management, and GitHub Discussions integration.

not rated 2 2mo ago A tokens not measured original MIT

team-up

5576

nvandessel/team-up

Skill Claude CodeCodex

Orchestrate persistent agent teams with TeamCreate. Use when the user says "team up", "spin up a team", or invokes /team-up.

not rated 2 5mo ago A 34 tokens original MIT

deep

5578

kbichave/skills

Plugin Claude Code

Bundles 4 skills, 17 agents, 6 hooks · 1,448 tokens together

Discover, plan, and implement complex systems with AI-assisted research, multi-LLM review, TDD sections, and disciplined execution.

not rated 2 changed 4d ago A tokens not measured original MIT

agn

5579

AgentureHQ/agenture-loop

Plugin Claude Code

Bundles 9 skills, 2 agents · 589 tokens together

Agentic SDLC for Claude Code — Claude facilitates writing specs and designing architecture, then autonomously builds implementation plans, implements and tests the product. Driven by structured /agn: skills with built-in review gates and document consistency.

not rated 2 3mo ago A tokens not measured original Apache-2.0

xllm

5580

kimmingul/xllm

Plugin Claude Code

Bundles 7 skills · 587 tokens together

Cross-vendor LLM advisors for Claude Code: ask codex, gemini, grok, cursor, or local ollama/lmstudio from inside a session and synthesize their independent opinions. Read-only by default.

not rated 2 27d ago A tokens not measured original MIT

sodam-loop

5581

sodam-ai/SoDam-Loop-Eng

Plugin Claude Code

Bundles 9 skills, 9 commands, 1 agent, 4 hooks · 878 tokens together

A Korean-language safety loop for non-developers who ask an AI to keep repairing a task until it works. Its description says it currently supports a single repair mode with 14 safety guardrails enabled by default.

not rated 2 changed 16d ago A tokens not measured

volley

5583

Ryan-M-Frank/volley

Plugin Claude Code

Bundles 8 skills, 1 MCP server · 516 tokens together

Two AI coding assistants in one repo, behind a hard lock. Claude and OpenAI Codex plan, implement, and review each other's work without colliding.

not rated 2 1mo ago A tokens not measured original Apache-2.0

mcp-development

5585

floriscornel/todo-mcp

Cursor rule Cursor

Cursor rule "mcp-development" from floriscornel/todo-mcp, covering mcp development patterns, tool definition structure, error handling patterns, tool naming conventions and response formatting.

not rated 2 7mo ago A 368 tokens original MIT

jbang-mcp-server

5586

glaforge/java-stdio-mcp-server

Skill Claude CodeCodex

Scaffolds and installs zero boilerplate Java-based MCP STDIO servers using JBang and LangChain4j for Gemini CLI. Use this to quickly bootstrap an MCP server from scratch.

not rated 2 6mo ago B 43 tokens

Clockwork-Innovations/simply-mcp

Skill Claude Code

Build Simply-MCP servers with createTool(), createResourceTemplate(), code execution mode, or MCP Apps. Use when creating MCP servers, testing tool handlers, writing simply-mcp test harnesses, building servers where AI composes tool calls into JavaScript, deploying MCP servers to Cloudflare Workers, or creating…

not rated 2 4mo ago A 74 tokens

mcp-reconnect

5590

palios-taey/mcp-reconnect

Plugin Claude Code

Bundles 1 skill · 37 tokens together

Reconnect MCP servers in Claude Code tmux sessions via automated key injection. No API required — works by driving the /mcp interactive menu through tmux send-keys.

not rated 2 1mo ago A tokens not measured original MIT

refactor

5591

zircote-plugins/refactor

Plugin Claude Code

Bundles 3 skills, 7 agents · 563 tokens together

Swarm-orchestrated code refactoring and feature development with specialist agents. Supports multi-instance parallel agent spawning, blackboard context sharing, and interactive development gates.

not rated 2 3mo ago A tokens not measured original MIT

matilha

5592

danilods/matilha-skills

Plugin Claude Code

Bundles 12 skills, 10 commands, 2 agents, 1 hook · 986 tokens together

You lead. Agents hunt. A cognitive + methodological harness for building complex AI-assisted projects — 11 phase-gated core skills, composition layer with plugin-namespace detection, SessionStart hook for cross-workspace activation, and 7 companion packs shipping 128 skills across UX, growth, agent architecture…

not rated 2 4mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: